About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Advanced Real Time Imaging for Materials Science and Processing
|
| Presentation Title |
Multimodal Operando/In Situ Characterizations of Dynamic Surface Reactions of Metals and Alloys |
| Author(s) |
Judith C. Yang, Brian Lee, Xiaobo Chen, Xiaohui Qu, Meng Li, Dmitri Zakharov, Wissam Saidi, Xidong Chen |
| On-Site Speaker (Planned) |
Judith C. Yang |
| Abstract Scope |
The rapid advancement of in situ electron microscopy now enables direct observation of dynamic processes such as oxidation, corrosion, and heterogeneous catalysis with unprecedented spatial and temporal resolution. However, these capabilities generate vast datasets that are time-consuming to analyze using traditional manual methods. Machine learning (ML) offers a powerful solution—automating interpretation, enhancing signal quality, and scaling with experimental throughput to extract fundamental insights from this data deluge. We present a few vignettes demonstrating the application of ML to real-time, atomic-resolution transmission electron microscopy (TEM), enabling robust and accelerated analysis of structural evolution under reactive conditions, such as metal and alloy oxidation as well as catalysis. These ML-accelerated workflows are broadly deployable for in situ electron microscopy, notably for energy and environmental technologies. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Machine Learning, Characterization, Nanotechnology |